CE400133T2B1 AIoT global manufacturer Advantech is proud to introduce a new breakthrough in Open Standard Module (OSM) – ROM-2860 core board. The ROM-2860 comes in an LGA package for an ultra-compact size design of 45 x 45 mm. Small in size but with extraordinary performance, it is equipped with Qualcomm’s eight-core QCS6490 processor, reaching a new level of performance and bringing breakthroughs to AIoT portable applications. Designed to exceed industry standards, the ROM-2860 enhances AI computing performance and brings new possibilities for machine vision intelligence solutions. With a wide selection of interfaces, the ROM-2860 provides the ideal solution for the diverse needs of AIoT scenarios.
Super small size, extraordinary performance
Featuring an ultra-compact OSM Size-L Size (45 x 45 mm), the ROM-2860 stands out for its outstanding performance among core boards of the same size. The Qualcomm octe-core QCS6490 processor with 6.9W TDP outperforms traditional core modules and meets a variety of industrial and portable applications such as HMI and embedded machine vision with its tiny size. Notably, the QCS6490 delivers nearly 20% higher performance than a mid-range x86 processor while significantly reducing power consumption by 43-75%.
In addition, by supporting Windows 11 on Arm, the ROM-2860 fully exploits the potential of the Arm architecture, extending battery life and ensuring stable performance output. Arm systems (SOCs) typically have basic features such as cpus, Gpus, Wi-Fi, mobile data networks, and neural processor units (Npus) to handle AI workloads, which provides useCE400133T2B1 rs with seamless compatibility with existing applications and tools on new Arm devices.
Edge AI empowers machine vision solutions
With 13 TOPS AI computing power, support for dual camera input and hardware video codec, the ROM-2860 can meet a variety of embedded machine vision needs. This small size solution, complemented by AI capabilities, performs well in applications that require seamless video capture, low-latency signals, limited installation space, and vibration resistance.
Compared to traditional devices, the ROM-2860 edge end AI solution improves the operational efficiency of applications such as autonomous mobile robots (AMR). These robots use cameras, radar, and lidar for initial AI modeling, and then gain reasoning capabilities to complete tasks such as object detection, route optimization, positioning, and collision avoidance.
ROM-2860 also supports various development tools such as Microsoft Azure AI Services, Qualcomm SCE400133T2B1 napdragon Neural Processing Engine (SNPE) SDK, and Qualcomm AI Hub. Simplify machine learning deployments and transform models from Aware, Azure, and other cloud service providers. Adopts Qualcomm QCS6490 CPU to provide 64-bit program support. Developers can update Visual Studio to version 15.9 or later for Arm 64 compatibility, simplifying binary compilation of existing projects.
Rich interfaces and smooth connections meet AIoT application requirements
The ROM-2860 supports a variety of interfaces, including PCIe Gen3 for 5G/Wi-Fi 6, LPDDR5, UFS, USB 3.2, URAT, GPIO and more. In addition, it offers dual display capabilities that support up to 2K resolutions, including DSI, DP, and eDP. A wide selection of I/O interfaces facilitates seamless connectivity within AIoT applications.
